# Denevil: Towards Deciphering and Navigating the Ethical Values of Large Language Models via Instruction Learning

arXiv: https://arxiv.org/abs/2310.11053 · HTML: https://mlsanity.com/paper/2310.11053/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 71 of its 118 references that are in the map.
- First posted on arXiv 17 Oct 2023.

## Builds on (most cited first, 30 of 71)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [GLM: General Language Model Pretraining with Autoregressive Blank Infilling](https://mlsanity.com/paper/2103.10360/) (2021)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset](https://mlsanity.com/paper/2307.04657/) (2023)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing](https://mlsanity.com/paper/2305.11738/) (2023)
- [A Tutorial on Bayesian Optimization](https://mlsanity.com/paper/1807.02811/) (2018)
- [Aligning AI With Shared Human Values](https://mlsanity.com/paper/2008.02275/) (2020)
- [Texygen: A Benchmarking Platform for Text Generation Models](https://mlsanity.com/paper/1802.01886/) (2018)
- [RRHF: Rank Responses to Align Language Models with Human Feedback without tears](https://mlsanity.com/paper/2304.05302/) (2023)
- [Artificial Intelligence, Values and Alignment](https://mlsanity.com/paper/2001.09768/) (2020)
- [Sliced Score Matching: A Scalable Approach to Density and Score Estimation](https://mlsanity.com/paper/1905.07088/) (2019)
- [Self-critiquing models for assisting human evaluators](https://mlsanity.com/paper/2206.05802/) (2022)
- [GeDi: Generative Discriminator Guided Sequence Generation](https://mlsanity.com/paper/2009.06367/) (2020)
- [FUDGE: Controlled Text Generation With Future Discriminators](https://mlsanity.com/paper/2104.05218/) (2021)

## Built on by (most cited first, 26 of 26)

- [PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action](https://mlsanity.com/paper/2409.00138/) (2024)
- [A Survey of Useful LLM Evaluation](https://mlsanity.com/paper/2406.00936/) (2024)
- [CLAVE: An Adaptive Framework for Evaluating Values of LLM Generated Responses](https://mlsanity.com/paper/2407.10725/) (2024)
- [Internal Value Alignment in Large Language Models through Controlled Value Vector Activation](https://mlsanity.com/paper/2507.11316/) (2025)
- [Beyond Human Norms: Unveiling Unique Values of Large Language Models through Interdisciplinary Approaches](https://mlsanity.com/paper/2404.12744/) (2024)
- [A Survey on Human-Centric LLMs](https://mlsanity.com/paper/2411.14491/) (2024)
- [The Staircase of Ethics: Probing LLM Value Priorities through Multi-Step Induction to Complex Moral Dilemmas](https://mlsanity.com/paper/2505.18154/) (2025)
- [Do Psychometric Tests Work for Large Language Models? Evaluation of Tests on Sexism, Racism, and Morality](https://mlsanity.com/paper/2510.11254/) (2025)
- [Value Compass Benchmarks: A Platform for Fundamental and Validated Evaluation of LLMs Values](https://mlsanity.com/paper/2501.07071/) (2025)
- [MoVa: Towards Generalizable Classification of Human Morals and Values](https://mlsanity.com/paper/2509.24216/) (2025)
- [Mitigating Biases in Language Models via Bias Unlearning](https://mlsanity.com/paper/2509.25673/) (2025)
- [Strong Preferences Affect the Robustness of Preference Models and Value Alignment](https://mlsanity.com/paper/2410.02451/) (2024)
- [AdAEM: An Adaptively and Automated Extensible Measurement of LLMs' Value Difference](https://mlsanity.com/paper/2505.13531/) (2025)
- [One Model, Many Morals: Uncovering Cross-Linguistic Misalignments in Computational Moral Reasoning](https://mlsanity.com/paper/2509.21443/) (2025)
- [Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communities](https://mlsanity.com/paper/2604.05339/) (2026)
- [Controllable Value Alignment in Large Language Models through Neuron-Level Editing](https://mlsanity.com/paper/2602.07356/) (2026)
- [A Survey on Training-free Alignment of Large Language Models](https://mlsanity.com/paper/2508.09016/) (2025)
- [Beyond Ethical Alignment: Evaluating LLMs as Artificial Moral Assistants](https://mlsanity.com/paper/2508.12754/) (2025)
- [IROTE: Human-like Traits Elicitation of Large Language Model via In-Context Self-Reflective Optimization](https://mlsanity.com/paper/2508.08719/) (2025)
- [Psychologically Enhanced AI Agents](https://mlsanity.com/paper/2509.04343/) (2025)
- [Implicit Values Embedded in How Humans and LLMs Complete Subjective Everyday Tasks](https://mlsanity.com/paper/2510.03384/) (2025)
- [D2VBench: Benchmarking Large Language Models with Value Dilemmas in Daily Scenarios](https://mlsanity.com/paper/2607.19834/) (2026)
- [Dialectics of Alignment: Harnessing Unsafe Knowledge for Dynamic Safety Routing](https://mlsanity.com/paper/2606.00686/) (2026)
- [Moral Safety in LLMs: Exposing Performative Compliance with Puzzled Cues](https://mlsanity.com/paper/2606.31644/) (2026)
- [How do LLMs Evaluate Perceived Moral Agency? Investigating Moral Decision-Making in Human-Artificial Agents Interactions](https://mlsanity.com/paper/2609.05037/) (2026)
- [Same Values, Different Languages? From Multilingual Probing to Steering LLMs Toward Chinese Social Values](https://mlsanity.com/paper/2609.08515/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have made unprecedented breakthroughs, yet their increasing integration into everyday life might raise societal risks due to generated unethical content. Despite extensive study on specific issues like bias, the intrinsic values of LLMs remain largely unexplored from a moral philosophy perspective. This work delves into ethical values utilizing Moral Foundation Theory. Moving beyond conventional discriminative evaluations with poor reliability, we propose DeNEVIL, a novel prompt generation algorithm tailored to dynamically exploit LLMs' value vulnerabilities and elicit the violation of ethics in a generative manner, revealing their underlying value inclinations. On such a basis, we construct MoralPrompt, a high-quality dataset comprising 2,397 prompts covering 500+ value principles, and then benchmark the intrinsic values across a spectrum of LLMs. We discovered that most models are essentially misaligned, necessitating further ethical value alignment. In response, we develop VILMO, an in-context alignment method that substantially enhances the value compliance of LLM outputs by learning to generate appropriate value instructions, outperforming existing competitors. Our methods are suitable for black-box and open-source models, offering a promising initial step in studying the ethical values of LLMs.